R Notebook

library(tidyverse)
library(lubridate)
library(plotly)
library(ggrepel)
df <- read_csv("covid_19_clean_complete.csv")

Parsed with column specification:
cols(
  `Province/State` = col_character(),
  `Country/Region` = col_character(),
  Lat = col_double(),
  Long = col_double(),
  Date = col_character(),
  Confirmed = col_double(),
  Deaths = col_double(),
  Recovered = col_double()
)

pop <- read.csv("API_SP.POP.TOTL_DS2_en_csv_v2_936048.csv")
pop <- tibble(country = pop$Country.Name, pop = pop$X2018)
tests <- read_csv("full-list-covid-19-tests-per-day.csv") %>%
  mutate(tests = `Daily change in cumulative total tests`)

Parsed with column specification:
cols(
  Entity = col_character(),
  Code = col_character(),
  Date = col_character(),
  `Daily change in cumulative total tests` = col_double()
)

options(scipen=999)

covid = df %>%
  mutate(Date = mdy(Date)) %>%
  group_by(`Country/Region`, Date) %>%
  summarise(Confirmed = sum(Confirmed, na.rm = T),
            Deaths = sum(Deaths, na.rm = T),
            Recovered = sum(Recovered, na.rm = T)) %>%
  arrange(`Country/Region`, Date)


final = covid %>%
  group_by(`Country/Region`) %>%
  filter(Confirmed >= 100) %>%
  mutate(hunfirst = if_else( Date == min(Date), 1, 0),
         days_since_hun = row_number(),
         marginal_confirmed = Confirmed - lag(Confirmed)) %>%
  left_join( pop %>%
               mutate(country = case_when(
                 country == "United States" ~ "US",
                 country == "Korea, Rep." ~ "South Korea",
                 TRUE ~ as.character(country))), 
             by = c("Country/Region" = "country")) %>%
  drop_na() %>%
  mutate(confirmed_permil = Confirmed/pop*1000000,
         deaths_permil = Deaths/pop*1000000,
         marginal_confirmed_permil = confirmed_permil - lag(confirmed_permil)) %>%
  left_join(tests %>%
              mutate(Date = mdy(Date),
                     Entity = if_else(Entity == "United States", "US", Entity)) %>%
              select(Entity, Date, tests), by = c("Country/Region" = "Entity", "Date"))


final = final %>%
  left_join(final %>%
              filter(confirmed_permil >= 20) %>%
              group_by(`Country/Region`) %>%
              mutate(days_sinc_twcon = row_number()))

Joining, by = c("Country/Region", "Date", "Confirmed", "Deaths", "Recovered", "hunfirst", "days_since_hun", "marginal_confirmed", "pop", "confirmed_permil", "deaths_permil", "marginal_confirmed_permil", "tests")

write_csv(final, "covid_final.csv")
  

graph_confirmed = final %>%
  filter(`Country/Region` %in% c("US", "China", "Italy", "Spain", "Germany", "France", "Israel", "Sweden", "Japan", "United Kingdom", "South Korea"),
         days_since_hun < 60) %>%
  ggplot(aes(x = days_since_hun, y = Confirmed, color = `Country/Region`)) + 
  geom_line() + scale_y_log10() + 
  theme_minimal() 
  

last = final %>%
  filter(`Country/Region` %in% c("US", "China", "Italy", "Spain", "Germany", "France", "Israel", "Sweden", "Japan", "United Kingdom", "South Korea"),
         days_since_hun < 60) %>%
  group_by(`Country/Region`) %>%
  filter(days_since_hun == max(days_since_hun))

graph = graph_confirmed + 
  geom_text(aes(x = days_since_hun + 2, y = Confirmed, color = `Country/Region`, label = `Country/Region`), data = last, check_overlap = TRUE) +
  theme(legend.position = "none") + 
  labs(title = "Confirmed cases by days since 100th case", x = "", y = "")


  
  
plotly = plotly_build(graph)
plotly$height = 900
plotly$width = 1100
plotly$sizingPolicy$defaultWidth = 1100
plotly$sizingPolicy$defaultHeight = 900
plotly

NA

graph_confirmed = final %>%
  filter(`Country/Region` %in% c("US", "China", "Italy", "Spain", "Germany", "France", "Israel", "Sweden", "Japan", "United Kingdom", "South Korea"),
         days_since_hun < 60) %>%
  ggplot(aes(x = days_since_hun, y = marginal_confirmed, color = `Country/Region`)) + 
  geom_smooth(se=F) + scale_y_log10() + 
  theme_minimal() 
  


graph = graph_confirmed + 
  geom_text(aes(x = days_since_hun + 2, y = marginal_confirmed, color = `Country/Region`, label = `Country/Region`), data = last, check_overlap = TRUE) + 
  theme(legend.position = "none") + 
  labs(title = "Marginal confirmed cases by days since 100th case", x = "", y = "")


  
  
plotly = plotly_build(graph)

Transformation introduced infinite values in continuous y-axis`geom_smooth()` using method = 'loess' and formula 'y ~ x'
Removed 9 rows containing non-finite values (stat_smooth).

plotly$height = 900
plotly$width = 1100
plotly$sizingPolicy$defaultWidth = 1100
plotly$sizingPolicy$defaultHeight = 900
plotly

graph_confirmed = final %>%
  filter(`Country/Region` %in% c("US", "China", "Italy", "Spain", "Germany", "France", "Israel", "Sweden", "Japan", "United Kingdom", "South Korea"),
         days_since_hun < 60) %>%
  ggplot(aes(x = days_sinc_twcon, y = confirmed_permil, color = `Country/Region`)) + 
  geom_line() + scale_y_log10() + 
  theme_minimal() 
  


graph = graph_confirmed + 
  geom_text(aes(x = days_sinc_twcon + 2, y = confirmed_permil, color = `Country/Region`, label = `Country/Region`), data = last, check_overlap = TRUE) + 
  theme(legend.position = "none") + 
  labs(title = "Confirmed per 1M cases by days since 20th case per 1M", x = "", y = "")


  
  
plotly = plotly_build(graph)
plotly$height = 900
plotly$width = 1100
plotly$sizingPolicy$defaultWidth = 1100
plotly$sizingPolicy$defaultHeight = 900
plotly

NA

graph_confirmed = final %>%
  filter(`Country/Region` %in% c("US", "China", "Italy", "Spain", "Germany", "France", "Israel", "Sweden", "Japan", "United Kingdom", "South Korea"),
         days_since_hun < 60) %>%
  ggplot(aes(x = days_sinc_twcon, y = marginal_confirmed_permil, color = `Country/Region`)) + 
  geom_smooth(se=F) + scale_y_log10() + 
  theme_minimal() 
  


graph = graph_confirmed + 
  geom_text(aes(x = days_sinc_twcon + 2, y = marginal_confirmed_permil, color = `Country/Region`, label = `Country/Region`), data = last, check_overlap = TRUE) + 
  theme(legend.position = "none") + 
  labs(title = "Marginal confirmed per 1M cases by days since 20th case per 1M", x = "", y = "")


  
  
plotly = plotly_build(graph)

Transformation introduced infinite values in continuous y-axis`geom_smooth()` using method = 'loess' and formula 'y ~ x'
Removed 123 rows containing non-finite values (stat_smooth).pseudoinverse used at 4neighborhood radius 2reciprocal condition number  0

plotly$height = 900
plotly$width = 1100
plotly$sizingPolicy$defaultWidth = 1100
plotly$sizingPolicy$defaultHeight = 900
plotly

NA

graph_confirmed = final %>%
  filter(`Country/Region` %in% c("US", "China", "Italy", "Spain", "Germany", "France", "Israel", "Sweden", "Japan", "United Kingdom", "South Korea"),
         days_since_hun < 60,
         !is.na(tests)) %>%
  ggplot(aes(x = days_since_hun, y = marginal_confirmed/tests, color = `Country/Region`)) + 
  geom_smooth(se = F) + scale_y_log10() + 
  theme_minimal() 
  


graph = graph_confirmed + 
  geom_text(aes(x = days_since_hun + 2, y = marginal_confirmed/tests, color = `Country/Region`, label = `Country/Region`), data = last, check_overlap = TRUE) + 
  theme(legend.position = "none") + 
  labs(title = "% of tests confirmed by days since 100th confirmed", x = "", y = "")


  
  
plotly = plotly_build(graph)

Transformation introduced infinite values in continuous y-axis`geom_smooth()` using method = 'loess' and formula 'y ~ x'
Removed 3 rows containing non-finite values (stat_smooth).

plotly$height = 900
plotly$width = 1200
plotly$sizingPolicy$defaultWidth = 1200
plotly$sizingPolicy$defaultHeight = 900
plotly